Resource Optimization Strategy for CPU Intensive Applications in Cloud Computing Environment

Abstract

Traditionally resource utilization on physical servers in cloud data center is uncertain. On one hand, resources will be wasted if the assignment of tasks are not enough. On the other hand it will cause overload if the assignment of tasks are too much. This is especially obvious when the applications are the same type. To solve this issue and considering CPU intensive application is one of the most common type of application in cloud, we have studied the optimization strategy for this kind of applications on the same server. According to resource preferences of different types of applications, we analyze the case that multiple CPU intensive applications run simultaneously, and put forward a model which can make a prediction of execution time for this case. Extensive experiments show that the model is suitable for CPU intensive applications, and it can accurately predict their execution time. In order to improve the execution efficiency of applications, we propose a scheduling model for CPU intensive applications. Experiments show that the scheduling model can improve the execution efficiency of applications effectively and optimize the resource utilization.